RESUMO
Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed by diagnostic variability, histopathology caseload, and shortage of pathologists. We sought to define the performance of an AI-based automated prostate cancer detection system, Paige Prostate, when applied to independent real-world data. The algorithm was employed to classify slides into two categories: benign (no further review needed) or suspicious (additional histologic and/or immunohistochemical analysis required). We assessed the sensitivity, specificity, positive predictive values (PPVs), and negative predictive values (NPVs) of a local pathologist, two central pathologists, and Paige Prostate in the diagnosis of 600 transrectal ultrasound-guided prostate needle core biopsy regions ('part-specimens') from 100 consecutive patients, and to ascertain the impact of Paige Prostate on diagnostic accuracy and efficiency. Paige Prostate displayed high sensitivity (0.99; CI 0.96-1.0), NPV (1.0; CI 0.98-1.0), and specificity (0.93; CI 0.90-0.96) at the part-specimen level. At the patient level, Paige Prostate displayed optimal sensitivity (1.0; CI 0.93-1.0) and NPV (1.0; CI 0.91-1.0) at a specificity of 0.78 (CI 0.64-0.89). The 27 part-specimens considered by Paige Prostate as suspicious, whose final diagnosis was benign, were found to comprise atrophy (n = 14), atrophy and apical prostate tissue (n = 1), apical/benign prostate tissue (n = 9), adenosis (n = 2), and post-atrophic hyperplasia (n = 1). Paige Prostate resulted in the identification of four additional patients whose diagnoses were upgraded from benign/suspicious to malignant. Additionally, this AI-based test provided an estimated 65.5% reduction of the diagnostic time for the material analyzed. Given its optimal sensitivity and NPV, Paige Prostate has the potential to be employed for the automated identification of patients whose histologic slides could forgo full histopathologic review. In addition to providing incremental improvements in diagnostic accuracy and efficiency, this AI-based system identified patients whose prostate cancers were not initially diagnosed by three experienced histopathologists. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.
Assuntos
Inteligência Artificial , Neoplasias da Próstata/diagnóstico , Idoso , Idoso de 80 Anos ou mais , Biópsia , Biópsia com Agulha de Grande Calibre , Humanos , Aprendizado de Máquina , Masculino , Pessoa de Meia-Idade , Patologistas , Próstata/patologia , Neoplasias da Próstata/patologiaRESUMO
STUDY DESIGN: Prospective, multicenter, randomized, and controlled Investigational Device Exemption clinical trial. OBJECTIVE: To compare the clinical safety and effectiveness of the selectively constrained SECURE-C (Globus Medical, Audubon, PA) Cervical Artificial Disc to anterior cervical discectomy and fusion (ACDF). SUMMARY OF BACKGROUND DATA: Cervical total disc replacement has been developed as an alternative to ACDF by allowing segmental motion. Current cervical total disc replacement designs incorporate constrained and unconstrained metal-on-metal or metal-on-polymer articulating designs with various means of fixation. METHODS: A total of 380 patients from 18 investigational sites were prospectively enrolled in the study. Patients were randomized, treated surgically, and evaluated postoperatively at 6 weeks, 3 months, 6 months, 12 months, and 24 months. Clinical outcomes include overall success, visual analogue scale pain (right arm, left arm, and neck), neck disability index, neurological status, Short Form 36 (SF-36) Health Status Survey questionnaires, range of motion, and adverse events. Bayesian statistical methods were used to analyze the outcomes. RESULTS: Overall success results demonstrated statistical superiority of the randomized SECURE-C group compared with the randomized ACDF group at 24 months, with a posterior probability of 100% using the protocol-specified criteria and 98.1% using Food and Drug Administration-defined criteria. At 24 months postoperatively, SECURE-C demonstrated clinically significant improvement in pain and function in terms of neck disability index, visual analogue scale, and 36-Item Short Form Health Survey. At 24 months, the percentage of patients experiencing secondary surgical interventions at the index level was statistically lower for the SECURE-C group (2.5%) than the ACDF group (9.7%). At 24 months, 84.6% of as-treated SECURE-C patients were range-of-motion successes. Satisfaction was high among SECURE-C patients. CONCLUSION: The selectively constrained SECURE-C Cervical Artificial Disc is as safe and effective as the standard of care, an anterior cervical discectomy and fusion. SECURE-C is statistically superior in terms of overall success, index-level subsequent surgical procedures, and patient satisfaction, making it an attractive surgical option for patients with symptomatic cervical disc disease. LEVEL OF EVIDENCE: 1.